Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    最

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     яких
    -0.07
    _jobs
    -0.06
    ouden
    -0.06
     DWORD
    -0.06
     Myers
    -0.06
     instancia
    -0.06
    oundary
    -0.06
    spb
    -0.06
    нося
    -0.05
    onal
    -0.05
    POSITIVE LOGITS
     ['-
    0.07
    нить
    0.06
     article
    0.06
     Quick
    0.06
     stones
    0.06
    .isRequired
    0.06
    essim
    0.06
     wrink
    0.06
     Hu
    0.06
    (plot
    0.06
    Act Density 0.008%

    No Known Activations